© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56023
    Prev
    Next
    INDEX
    Explanations

    virtually + adjective/preposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç³Ł
    -0.10
    ips
    -0.10
    arp
    -0.09
    å¾Ģå¾Ģ
    -0.09
     truth
    -0.08
    liness
    -0.08
    haps
    -0.08
    å°¤åħ¶
    -0.08
     вполне
    -0.08
    å¾Ģå¾Ģä¼ļ
    -0.08
    POSITIVE LOGITS
    ä½ľèĢħæīĢæľī
    0.11
    å¼ĢéŨ
    0.10
    家åĸ»æĪ·æĻĵ
    0.10
    ories
    0.10
    -minded
    0.10
    że
    0.10
    åľ°æĿ¿
    0.10
    ä¹Łæ²¡ä»Ģä¹Ī
    0.10
    没ä»Ģä¹Ī
    0.09
    åºĹéĩĮ
    0.09
    Activations Density 0.006%

    No Known Activations